# Hypothesis Identification in Dialogues on MedQA (test)

Source: [Hypothesis Identification in Dialogues on MedQA (test)](<https://www.sota2.com/research/sota/hypothesis-identification-in-dialogues-on-medqa-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-09T07:49:36.296Z

Evaluation of model performance on the test split of the MedQA dataset for identifying hypotheses within medical dialogues, measured by Success Rate and Average Turns.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Hypothesis identification in dialogues |
| Dataset (including any stated split) | MedQA Medical domain (test) |
| Metric | Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Success Rate](<https://www.sota2.com/research/sota/hypothesis-identification-in-dialogues-on-medqa-test.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Turns](<https://www.sota2.com/research/sota/hypothesis-identification-in-dialogues-on-medqa-test.md?metric=Average%20Turns>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| INFOGATHERER | 69.3 | Not recorded | 69ae53d82d603e6de3e427ff |
| INFOGATHERER | 68.1 | Not recorded | 69ae53d82d603e6de3e427ff |
| IG Bayesian | 67.5 | Not recorded | 69ae53d82d603e6de3e427ff |
| IG Bayesian | 64.2 | Not recorded | 69ae53d82d603e6de3e427ff |
| UoT | 63.8 | Not recorded | 69ae53d82d603e6de3e427ff |
| UoT | 59.5 | Not recorded | 69ae53d82d603e6de3e427ff |
| MediQ | 59.1 | Not recorded | 69ae53d82d603e6de3e427ff |
| MediQ | 56.4 | Not recorded | 69ae53d82d603e6de3e427ff |
| AoP | 41.6 | Not recorded | 69ae53d82d603e6de3e427ff |
| AoP | 39.2 | Not recorded | 69ae53d82d603e6de3e427ff |

### INFOGATHERER

Success Rate: 69.3. Result ID: 69ae7ade6dbb7075b95656fe.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"gpt-5-nano"}. This record does not assert independent reproduction.

### INFOGATHERER

Success Rate: 68.1. Result ID: 69ae7ade6dbb7075b9565703.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"Qwen3 32B"}. This record does not assert independent reproduction.

### IG Bayesian

Success Rate: 67.5. Result ID: 69ae7ade6dbb7075b95656fd.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"gpt-5-nano"}. This record does not assert independent reproduction.

### IG Bayesian

Success Rate: 64.2. Result ID: 69ae7ade6dbb7075b9565702.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"Qwen3 32B"}. This record does not assert independent reproduction.

### UoT

Success Rate: 63.8. Result ID: 69ae7ade6dbb7075b95656fc.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"gpt-5-nano"}. This record does not assert independent reproduction.

### UoT

Success Rate: 59.5. Result ID: 69ae7ade6dbb7075b9565701.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"Qwen3 32B"}. This record does not assert independent reproduction.

### MediQ

Success Rate: 59.1. Result ID: 69ae7ade6dbb7075b95656fb.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa759c1e209131cea68f2f.md>)

[Implementation](<https://github.com/stellali7/MediQ>)

Recorded evaluation configuration: {"Model":"gpt-5-nano"}. This record does not assert independent reproduction.

### MediQ

Success Rate: 56.4. Result ID: 69ae7ade6dbb7075b9565700.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa759c1e209131cea68f2f.md>)

[Implementation](<https://github.com/stellali7/MediQ>)

Recorded evaluation configuration: {"Model":"Qwen3 32B"}. This record does not assert independent reproduction.

### AoP

Success Rate: 41.6. Result ID: 69ae7ade6dbb7075b95656fa.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"gpt-5-nano"}. This record does not assert independent reproduction.

### AoP

Success Rate: 39.2. Result ID: 69ae7ade6dbb7075b95656ff.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d82d603e6de3e427ff.md>)

Recorded evaluation configuration: {"Model":"Qwen3 32B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
